Ethics and Social Responsibility in AI-Assisted Interviewing: An LLM-in-the-Loop Study of AI-Generated Follow-Up Questions
For qualitative researchers and interview practitioners, this work highlights critical ethical risks in AI-assisted interviewing that must be addressed before deployment.
This paper presents an LLM-in-the-loop Wizard-of-Oz study simulating an AI follow-up assistant in live interviews, identifying five interlocking ethical concerns including harmful language, disrespect, participation inequality, unclear responsibility, and privacy risks. The findings inform design and governance implications for safer AI-assisted interviewing.
Semi-structured interviews rely on timely, context-sensitive follow-up questions, yet interviewers' cognitive load and limited domain familiarity can constrain probing depth. We report findings from an LLM-in-the-loop Wizard-of-Oz (WoZ) study that simulates an AI follow-up assistant in live interviewing while preserving human oversight. In our setup, a co-interviewer selectively relayed and could edit AI-generated follow-up questions (AGQs) produced in real time by GPT-4o, enabling a realistic approximation of deployment without fully automating the interaction. Across 17 interviewers with varied qualitative-method expertise, participants raised five interlocking concerns: (1) harmful or discriminatory language and unpredictable interaction harms, (2) undermining interviewees' sense of respect through divided attention and missing nonverbal cues, (3) technology-based participation inequality, (4) unclear responsibility when harms occur, and (5) privacy, disclosure, and compliance risks when AI listens, records, or transcribes sensitive content. We translate these concerns into design and governance implications for safer, more respectful, and more accountable AI-assisted interviewing.